检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024

作者： Lee, Yu-En Fan, Chih-Peng National Chung Hsing University Master Program in Semiconductor and Green Technology Taichung Taiwan National Chung Hsing University Department of Electrical Engineering Taichung Taiwan

ISBN: (纸本)9798331530839

In this paper, a deep-learning based pose estimation technology for recognizing user's interests on interactive advertising displays is developed by leveraging the YOLO-Pose architecture. The primary goal is to predict user's attention areas by analyzing angular relationships with human body poses. The methodology uses the YOLO-Pose model to identify 17 keypoints on the human body and the angles among the selected body keypoints are calculated. The proposed design incorporates the left and right hand identification and the height determination to address accuracy issues from variations in user's height or body size. By integrating the estimation data for angles, user's height, and handedness, the horizontal and vertical SVM classifiers will be pre-trained. After the SVM classifiers are well trained, the combination results from both SVM classifiers enables the prediction of the user's area of interests. Experimental results with four, six, and eight grid divisions on the display reveals that the average identifying accuracies for horizontal and vertical grid classification can be up to 94% and 83%, respectively. By height adjusted information, the horizontal and vertical classification accuracies of the SVM classifiers can improve by 11% and 20% respectively within corresponding height ranges. For the embedded device implementation, the YOLO model and SVM classifier are deployed on the Jetson AGX Orin platform to achieve an average processing speed of 15 frames per second. © 2024 IEEE.

关键词： Marketing

来源：评论

学校读者我要写书评

暂无评论

An Efficient Reconfigurable Parameterized Convolutional Neural Network Accelerator on FPGA Platform

An Efficient Reconfigurable Parameterized Convolutional Neur...

引用

2025 IEEE International Conference on Consumer Electronics, ICCE 2025

作者： Lai, Yeong-Kang Lin, Chien-Hung Department of the Electrical Engineering Master Program in Semiconductor and Green Technology National Chung Hsing University Taichung Taiwan

ISBN: (纸本)9798331521165

This paper presents an efficient reconfigurable parameterized convolutional neural network (CNN) accelerator designed for FPGA platforms. The core of the accelerator allows flexible adjustments of input channel parallelism (Pc) and convolution filter parallelism (Pn) to meet the needs of various CNN models, optimizing both resource utilization and computational efficiency. The architecture is applied specifically to infrared (IR) and visible light (VI) image fusion, enabling real-time processing on an FPGA with significantly reduced latency. Experimental results demonstrate that the accelerator reduces latency to 192 ms while maintaining high image quality, achieving efficient image fusion on the FPGA platform. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Efficient Reconfigurable Parameterized Convolutional Neural Network Accelerator on FPGA Platform

An Efficient Reconfigurable Parameterized Convolutional Neur...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Yeong-Kang Lai Chien-Hung Lin Department of the Electrical Engineering Master Program in Semiconductor and Green Technology National Chung Hsing University Taichung Taiwan R.O.C

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

关键词： Image quality Convolution Computer architecture Parallel processing Real-time systems Convolutional neural networks Resource management Image fusion Field programmable gate arrays Hardware acceleration

来源：评论

学校读者我要写书评

暂无评论

Identification of User's Interests by Deep-Learning Based Pose Estimation with Angle Relationship from Keypoints for Smart Advertising Displays

Identification of User's Interests by Deep-Learning Based Po...

引用

IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia)

作者： Yu-En Lee Chih-Peng Fan Master Program in Semiconductor and Green Technology National Chung Hsing University Taichung Taiwan Department of Electrical Engineering National Chung Hsing University Taichung Taiwan

ISBN: (数字)9798331530839

ISBN: (纸本)9798331530846

关键词： Support vector machines YOLO Accuracy Feature detection Pose estimation Classification algorithms Advertising

来源：评论

学校读者我要写书评

暂无评论

A Data Encryption System Utilizing Physical Unclonable Functions, Pseudorandom Functions, and Ascon

A Data Encryption System Utilizing Physical Unclonable Funct...

引用

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Yian Chen Yichiao Chen Hongzhe Chen Yeong-Kang Lai Master Program in Semiconductor and Green Technology National Chung Hsing University Taichung Taiwan Department of Electrical Engineering National Chung Hsing University Taichung Taiwan

ISBN: (数字)9798350386844

ISBN: (纸本)9798350386851

This study presents a data encryption transmission system designed to achieve high security, integrating Physical Unclonable Functions (PUF), Pseudo-Random Functions (PRF), and the Ascon encryption standard. The system utilizes Weak PUF for key generation, based on the unique physical characteristics of devices to produce unpredictable and device-specific responses. Furthermore, the system employs a PRF designed based on PUF characteristics to generate Nonce, further enhancing the security of the communication process. The choice of Ascon encryption mode is based on its high efficiency and low resource consumption, making it an ideal option for maintaining high security while being suitable for resource-constrained devices.

关键词： Resistance Nonce Side-channel attacks Physical unclonable function Encryption Security System analysis and design

来源：评论

学校读者我要写书评

暂无评论

Upcycling electroplating sludge into nanoflower-structured Cu-MOFs for efficient Fenton-like degradation of organic dyes

引用

Journal of Water Process Engineering 2025年 75卷

作者： Lin, Jia-Yin Yu, Si-Han Shih, Jun-Ren Hsieh, Tsai-Hsuan Wang, Chih-Ying Huang, Jen-Yu Tsao, Nai-Wen Master and Doctoral Program in Semiconductor and Green Technology Academy of Circular Economy National Chung Hsing University Nantou 540 Taiwan Master and Doctoral Program in Industrial and Smart Technology Academy of Circular Economy National Chung Hsing University Nantou 540 Taiwan Master and Doctoral Program in Specialty Crops and Metabolomics Academy of Circular Economy National Chung Hsing University Nantou 540 Taiwan

The growing demand for sustainable strategies to address industrial pollution has spurred interest in converting hazardous solid wastes into functional materials. In this study, electroplating sludge (ES)—rich in copper and minor nickel—was successfully upcycled into two nanoflower-structured metal-organic frameworks (MOFs), ES-MOF-BDC and ES-MOF-BTC, via a solvothermal method using 1,4-benzenedicarboxylic acid (BDC) and benzene-1,3,5-tricarboxylic acid (BTC) as organic linkers. The resulting MOFs exhibited high crystallinity, mesoporous structures, and uniformly distributed Cu active sites. The hierarchical morphology effectively suppressed metal aggregation and enhanced the availability of catalytic sites. Among the two, ES-MOF-BTC demonstrated superior Fenton-like catalytic performance, achieving 95.76 % removal of Congo Red (CR) and complete degradation of methylene blue (MB) and Eriochrome Black T (EBT) within 60 min using only 1 mg of catalyst and 10 μL of H₂O₂. Kinetic analysis confirmed pseudo-first-order behavior, with a high turnover frequency (TOF = 0.0256 min−1) and low activation energy (24.25 kJ/mol). Scavenger experiments and EPR analysis confirmed hydroxyl radicals (•OH) as the dominant reactive species. The catalyst maintained over 85 % activity after ten reuse cycles and remained effective across various natural water matrices and under saline conditions. This work highlights a green and scalable strategy for transforming electroplating sludge into high-performance MOF catalysts, offering both environmental remediation potential and circular economy value in wastewater treatment applications. © 2025 Elsevier Ltd

关键词： Circular economy Congo Red degradation Copper-based MOF Electroplating sludge Fenton-like catalysis

来源：评论

学校读者我要写书评

暂无评论

Sustainable Bio-Adsorbent Generated from Coffee Waste for Dual Application in Heavy Metal and Dye Removal

引用

Processes 2025年第5期13卷 1364-1364页

作者： Jia-Yin Lin Pei-Tzu Chang Jun-Ren Shi Fu-Chen Liu Chih-Ying Wang Nai-Wen Tsao Master and Doctoral Program in Industrial and Smart Technology Academy of Circular Economy National Chung Hsing University Nantou 540 Taiwan Master and Doctoral Program in Semiconductor and Green Technology Academy of Circular Economy National Chung Hsing University Nantou 540 Taiwan Department of Environmental Engineering and Science Chia Nan University of Pharmacy and Science Tainan 717 Taiwan Master and Doctoral Program in Specialty Crops and Metabolomics Academy of Circular Economy National Chung Hsing University Nantou 540 Taiwan

Heavy metal and dye contamination from industrial wastewater present substantial dangers to both ecological systems and human well-being. This study explores the upcycling of Coffee Powder Trimmings (CPT), a biomass waste rich in oxygen-containing functional groups, for water remediation. CPT was first used to adsorb Cu2+ and Fe3+ ions, then pyrolyzed at 750 °C to form metal oxide biochar composites (Cu/CB and Fe/CB). Characterization confirmed the formation of CuO and Fe3O4 particles and the retention of key adsorption functionalities. The materials were evaluated for methylene blue (MB) removal across pH levels, various water bodies, and multiple reuse cycles. CPT effectively removed >95% of Cu2+ and Fe3+ via chelation, while Fe/CB achieved up to 97.8% MB removal due to synergistic π–π, hydrogen bonding, and coordination interactions. Both biochars retained high performance after five cycles, with Fe/CB maintaining 86.88% efficiency. These results highlight CPT-derived biochar as a sustainable, low-cost adsorbent for dual removal of heavy metals and dyes.

关键词： Coffee Powder Trimmings heavy metal dye removal

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：